吴恩达-机器学习-一元线性回归模型实现

吴恩达《机器学习》2022版 第一周 一元线性回归 房价预测简单实现

import numpy as np
import math, copy


#输入数据
x_train = np.array([1.0, 2.0])
y_train = np.array([300.0, 500.0])

#代价函数
def compute_cost(x, y, w, b): 

    m = x.shape[0] 
    
    cost_sum = 0 
    for i in range(m): 
        f_wb = w * x[i] + b   
        cost = (f_wb - y[i]) ** 2  
        cost_sum = cost_sum + cost  
    total_cost = (1 / (2 * m)) * cost_sum  

    return total_cost

#求偏导
def compute_gradient(x, y, w, b): 
  
    m = x.shape[0]    
    dj_dw = 0
    dj_db = 0
    
    for i in range(m):  
        f_wb = w * x[i] + b 
        dj_dw_i = (f_wb - y[i]) * x[i] 
        dj_db_i = f_wb - y[i] 
        dj_db += dj_db_i
        dj_dw += dj_dw_i 
    dj_dw = dj_dw / m 
    dj_db = dj_db / m 
        
    return dj_dw, dj_db

#梯度下降
def gradient_descent(x, y, w_in, b_in, alpha, num_iters, cost_function, gradient_function): 
   
    w = copy.deepcopy(w_in) # avoid modifying global w_in
    # An array to store cost J and w's at each iteration primarily for graphing later
    J_history = []
    p_history = []
    b = b_in
    w = w_in
    
    for i in range(num_iters):
        # Calculate the gradient and update the parameters using gradient_function
        dj_dw, dj_db = gradient_function(x, y, w , b)     

        # Update Parameters using equation (3) above
        b = b - alpha * dj_db                            
        w = w - alpha * dj_dw                            

        # Save cost J at each iteration
        if i<100000:      # prevent resource exhaustion 
            J_history.append( cost_function(x, y, w , b))
            p_history.append([w,b])
        # Print cost every at intervals 10 times or as many iterations if < 10
        if i% math.ceil(num_iters/10) == 0:
            print(f"Iteration {i:4}: Cost {J_history[-1]:0.2e} ",
                  f"dj_dw: {dj_dw: 0.3e}, dj_db: {dj_db: 0.3e}  ",
                  f"w: {w: 0.3e}, b:{b: 0.5e}")
 
    return w, b, J_history, p_history #return w and J,w history for graphing


#迭代寻找最优解
# initialize parameters
w_init = 0
b_init = 0
# some gradient descent settings
iterations = 10000
tmp_alpha = 1.0e-2
# run gradient descent
w_final, b_final, J_hist, p_hist = gradient_descent(x_train ,y_train, w_init, b_init, tmp_alpha, 
                                                    iterations, compute_cost, compute_gradient)
print(f"(w,b) found by gradient descent: ({w_final:8.4f},{b_final:8.4f})")

#预测
print(f"1000 sqft house prediction {w_final*1.0 + b_final:0.1f} Thousand dollars")
print(f"1200 sqft house prediction {w_final*1.2 + b_final:0.1f} Thousand dollars")
print(f"2000 sqft house prediction {w_final*2.0 + b_final:0.1f} Thousand dollars")